1 files changed, 141 insertions, 132 deletions

diff --git a/mm/zswap.c b/mm/zswap.c
index 841e35f1db2..008388fe7b0 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -77,18 +77,21 @@ static u64 zswap_duplicate_entry;
 **********************************/
 /* Enable/disable zswap (disabled by default, fixed at boot for now) */
 static bool zswap_enabled __read_mostly;
-module_param_named(enabled, zswap_enabled, bool, 0);
+module_param_named(enabled, zswap_enabled, bool, 0444);
 
 /* Compressor to be used by zswap (fixed at boot for now) */
 #define ZSWAP_COMPRESSOR_DEFAULT "lzo"
 static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
-module_param_named(compressor, zswap_compressor, charp, 0);
+module_param_named(compressor, zswap_compressor, charp, 0444);
 
 /* The maximum percentage of memory that the compressed pool can occupy */
 static unsigned int zswap_max_pool_percent = 20;
 module_param_named(max_pool_percent,
 			zswap_max_pool_percent, uint, 0644);
 
+/* zbud_pool is shared by all of zswap backend  */
+static struct zbud_pool *zswap_pool;
+
 /*********************************
 * compression functions
 **********************************/
@@ -160,14 +163,14 @@ static void zswap_comp_exit(void)
  * rbnode - links the entry into red-black tree for the appropriate swap type
  * refcount - the number of outstanding reference to the entry. This is needed
  *            to protect against premature freeing of the entry by code
- *            concurent calls to load, invalidate, and writeback.  The lock
+ *            concurrent calls to load, invalidate, and writeback.  The lock
  *            for the zswap_tree structure that contains the entry must
  *            be held while changing the refcount.  Since the lock must
  *            be held, there is no reason to also make refcount atomic.
  * offset - the swap offset for the entry.  Index into the red-black tree.
- * handle - zsmalloc allocation handle that stores the compressed page data
+ * handle - zbud allocation handle that stores the compressed page data
  * length - the length in bytes of the compressed page data.  Needed during
- *           decompression
+ *          decompression
  */
 struct zswap_entry {
 	struct rb_node rbnode;
@@ -189,7 +192,6 @@ struct zswap_header {
 struct zswap_tree {
 	struct rb_root rbroot;
 	spinlock_t lock;
-	struct zbud_pool *pool;
 };
 
 static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
@@ -202,7 +204,7 @@ static struct kmem_cache *zswap_entry_cache;
 static int zswap_entry_cache_create(void)
 {
 	zswap_entry_cache = KMEM_CACHE(zswap_entry, 0);
-	return (zswap_entry_cache == NULL);
+	return zswap_entry_cache == NULL;
 }
 
 static void zswap_entry_cache_destory(void)
@@ -217,6 +219,7 @@ static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
 	if (!entry)
 		return NULL;
 	entry->refcount = 1;
+	RB_CLEAR_NODE(&entry->rbnode);
 	return entry;
 }
 
@@ -225,19 +228,6 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
 	kmem_cache_free(zswap_entry_cache, entry);
 }
 
-/* caller must hold the tree lock */
-static void zswap_entry_get(struct zswap_entry *entry)
-{
-	entry->refcount++;
-}
-
-/* caller must hold the tree lock */
-static int zswap_entry_put(struct zswap_entry *entry)
-{
-	entry->refcount--;
-	return entry->refcount;
-}
-
 /*********************************
 * rbtree functions
 **********************************/
@@ -285,6 +275,60 @@ static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry,
 	return 0;
 }
 
+static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
+{
+	if (!RB_EMPTY_NODE(&entry->rbnode)) {
+		rb_erase(&entry->rbnode, root);
+		RB_CLEAR_NODE(&entry->rbnode);
+	}
+}
+
+/*
+ * Carries out the common pattern of freeing and entry's zbud allocation,
+ * freeing the entry itself, and decrementing the number of stored pages.
+ */
+static void zswap_free_entry(struct zswap_entry *entry)
+{
+	zbud_free(zswap_pool, entry->handle);
+	zswap_entry_cache_free(entry);
+	atomic_dec(&zswap_stored_pages);
+	zswap_pool_pages = zbud_get_pool_size(zswap_pool);
+}
+
+/* caller must hold the tree lock */
+static void zswap_entry_get(struct zswap_entry *entry)
+{
+	entry->refcount++;
+}
+
+/* caller must hold the tree lock
+* remove from the tree and free it, if nobody reference the entry
+*/
+static void zswap_entry_put(struct zswap_tree *tree,
+			struct zswap_entry *entry)
+{
+	int refcount = --entry->refcount;
+
+	BUG_ON(refcount < 0);
+	if (refcount == 0) {
+		zswap_rb_erase(&tree->rbroot, entry);
+		zswap_free_entry(entry);
+	}
+}
+
+/* caller must hold the tree lock */
+static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
+				pgoff_t offset)
+{
+	struct zswap_entry *entry = NULL;
+
+	entry = zswap_rb_search(root, offset);
+	if (entry)
+		zswap_entry_get(entry);
+
+	return entry;
+}
+
 /*********************************
 * per-cpu code
 **********************************/
@@ -303,7 +347,7 @@ static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu)
 			return NOTIFY_BAD;
 		}
 		*per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = tfm;
-		dst = kmalloc(PAGE_SIZE * 2, GFP_KERNEL);
+		dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
 		if (!dst) {
 			pr_err("can't allocate compressor buffer\n");
 			crypto_free_comp(tfm);
@@ -344,18 +388,18 @@ static int zswap_cpu_init(void)
 {
 	unsigned long cpu;
 
-	get_online_cpus();
+	cpu_notifier_register_begin();
 	for_each_online_cpu(cpu)
 		if (__zswap_cpu_notifier(CPU_UP_PREPARE, cpu) != NOTIFY_OK)
 			goto cleanup;
-	register_cpu_notifier(&zswap_cpu_notifier_block);
-	put_online_cpus();
+	__register_cpu_notifier(&zswap_cpu_notifier_block);
+	cpu_notifier_register_done();
 	return 0;
 
 cleanup:
 	for_each_online_cpu(cpu)
 		__zswap_cpu_notifier(CPU_UP_CANCELED, cpu);
-	put_online_cpus();
+	cpu_notifier_register_done();
 	return -ENOMEM;
 }
 
@@ -364,20 +408,8 @@ cleanup:
 **********************************/
 static bool zswap_is_full(void)
 {
-	return (totalram_pages * zswap_max_pool_percent / 100 <
-		zswap_pool_pages);
-}
-
-/*
- * Carries out the common pattern of freeing and entry's zsmalloc allocation,
- * freeing the entry itself, and decrementing the number of stored pages.
- */
-static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry)
-{
-	zbud_free(tree->pool, entry->handle);
-	zswap_entry_cache_free(entry);
-	atomic_dec(&zswap_stored_pages);
-	zswap_pool_pages = zbud_get_pool_size(tree->pool);
+	return totalram_pages * zswap_max_pool_percent / 100 <
+		zswap_pool_pages;
 }
 
 /*********************************
@@ -387,7 +419,7 @@ static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry)
 enum zswap_get_swap_ret {
 	ZSWAP_SWAPCACHE_NEW,
 	ZSWAP_SWAPCACHE_EXIST,
-	ZSWAP_SWAPCACHE_NOMEM
+	ZSWAP_SWAPCACHE_FAIL,
 };
 
 /*
@@ -401,9 +433,10 @@ enum zswap_get_swap_ret {
  * added to the swap cache, and returned in retpage.
  *
  * If success, the swap cache page is returned in retpage
- * Returns 0 if page was already in the swap cache, page is not locked
- * Returns 1 if the new page needs to be populated, page is locked
- * Returns <0 on error
+ * Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache
+ * Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated,
+ *     the new page is added to swapcache and locked
+ * Returns ZSWAP_SWAPCACHE_FAIL on error
  */
 static int zswap_get_swap_cache_page(swp_entry_t entry,
 				struct page **retpage)
@@ -475,7 +508,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
 	if (new_page)
 		page_cache_release(new_page);
 	if (!found_page)
-		return ZSWAP_SWAPCACHE_NOMEM;
+		return ZSWAP_SWAPCACHE_FAIL;
 	*retpage = found_page;
 	return ZSWAP_SWAPCACHE_EXIST;
 }
@@ -502,7 +535,7 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 	struct page *page;
 	u8 *src, *dst;
 	unsigned int dlen;
-	int ret, refcount;
+	int ret;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
@@ -513,27 +546,25 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 	zbud_unmap(pool, handle);
 	tree = zswap_trees[swp_type(swpentry)];
 	offset = swp_offset(swpentry);
-	BUG_ON(pool != tree->pool);
 
 	/* find and ref zswap entry */
 	spin_lock(&tree->lock);
-	entry = zswap_rb_search(&tree->rbroot, offset);
+	entry = zswap_entry_find_get(&tree->rbroot, offset);
 	if (!entry) {
 		/* entry was invalidated */
 		spin_unlock(&tree->lock);
 		return 0;
 	}
-	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 	BUG_ON(offset != entry->offset);
 
 	/* try to allocate swap cache page */
 	switch (zswap_get_swap_cache_page(swpentry, &page)) {
-	case ZSWAP_SWAPCACHE_NOMEM: /* no memory */
+	case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
 		ret = -ENOMEM;
 		goto fail;
 
-	case ZSWAP_SWAPCACHE_EXIST: /* page is unlocked */
+	case ZSWAP_SWAPCACHE_EXIST:
 		/* page is already in the swap cache, ignore for now */
 		page_cache_release(page);
 		ret = -EEXIST;
@@ -542,13 +573,13 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 	case ZSWAP_SWAPCACHE_NEW: /* page is locked */
 		/* decompress */
 		dlen = PAGE_SIZE;
-		src = (u8 *)zbud_map(tree->pool, entry->handle) +
+		src = (u8 *)zbud_map(zswap_pool, entry->handle) +
 			sizeof(struct zswap_header);
 		dst = kmap_atomic(page);
 		ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src,
 				entry->length, dst, &dlen);
 		kunmap_atomic(dst);
-		zbud_unmap(tree->pool, entry->handle);
+		zbud_unmap(zswap_pool, entry->handle);
 		BUG_ON(ret);
 		BUG_ON(dlen != PAGE_SIZE);
 
@@ -556,43 +587,44 @@ static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
 		SetPageUptodate(page);
 	}
 
+	/* move it to the tail of the inactive list after end_writeback */
+	SetPageReclaim(page);
+
 	/* start writeback */
 	__swap_writepage(page, &wbc, end_swap_bio_write);
 	page_cache_release(page);
 	zswap_written_back_pages++;
 
 	spin_lock(&tree->lock);
-
 	/* drop local reference */
-	zswap_entry_put(entry);
-	/* drop the initial reference from entry creation */
-	refcount = zswap_entry_put(entry);
+	zswap_entry_put(tree, entry);
 
 	/*
-	 * There are three possible values for refcount here:
-	 * (1) refcount is 1, load is in progress, unlink from rbtree,
-	 *     load will free
-	 * (2) refcount is 0, (normal case) entry is valid,
-	 *     remove from rbtree and free entry
-	 * (3) refcount is -1, invalidate happened during writeback,
-	 *     free entry
-	 */
-	if (refcount >= 0) {
-		/* no invalidate yet, remove from rbtree */
-		rb_erase(&entry->rbnode, &tree->rbroot);
-	}
+	* There are two possible situations for entry here:
+	* (1) refcount is 1(normal case),  entry is valid and on the tree
+	* (2) refcount is 0, entry is freed and not on the tree
+	*     because invalidate happened during writeback
+	*  search the tree and free the entry if find entry
+	*/
+	if (entry == zswap_rb_search(&tree->rbroot, offset))
+		zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
-	if (refcount <= 0) {
-		/* free the entry */
-		zswap_free_entry(tree, entry);
-		return 0;
-	}
-	return -EAGAIN;
 
+	goto end;
+
+	/*
+	* if we get here due to ZSWAP_SWAPCACHE_EXIST
+	* a load may happening concurrently
+	* it is safe and okay to not free the entry
+	* if we free the entry in the following put
+	* it it either okay to return !0
+	*/
 fail:
 	spin_lock(&tree->lock);
-	zswap_entry_put(entry);
+	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
+
+end:
 	return ret;
 }
 
@@ -620,7 +652,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 	/* reclaim space if needed */
 	if (zswap_is_full()) {
 		zswap_pool_limit_hit++;
-		if (zbud_reclaim_page(tree->pool, 8)) {
+		if (zbud_reclaim_page(zswap_pool, 8)) {
 			zswap_reject_reclaim_fail++;
 			ret = -ENOMEM;
 			goto reject;
@@ -647,7 +679,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 
 	/* store */
 	len = dlen + sizeof(struct zswap_header);
-	ret = zbud_alloc(tree->pool, len, __GFP_NORETRY | __GFP_NOWARN,
+	ret = zbud_alloc(zswap_pool, len, __GFP_NORETRY | __GFP_NOWARN,
 		&handle);
 	if (ret == -ENOSPC) {
 		zswap_reject_compress_poor++;
@@ -657,11 +689,11 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 		zswap_reject_alloc_fail++;
 		goto freepage;
 	}
-	zhdr = zbud_map(tree->pool, handle);
+	zhdr = zbud_map(zswap_pool, handle);
 	zhdr->swpentry = swp_entry(type, offset);
 	buf = (u8 *)(zhdr + 1);
 	memcpy(buf, dst, dlen);
-	zbud_unmap(tree->pool, handle);
+	zbud_unmap(zswap_pool, handle);
 	put_cpu_var(zswap_dstmem);
 
 	/* populate entry */
@@ -676,18 +708,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 		if (ret == -EEXIST) {
 			zswap_duplicate_entry++;
 			/* remove from rbtree */
-			rb_erase(&dupentry->rbnode, &tree->rbroot);
-			if (!zswap_entry_put(dupentry)) {
-				/* free */
-				zswap_free_entry(tree, dupentry);
-			}
+			zswap_rb_erase(&tree->rbroot, dupentry);
+			zswap_entry_put(tree, dupentry);
 		}
 	} while (ret == -EEXIST);
 	spin_unlock(&tree->lock);
 
 	/* update stats */
 	atomic_inc(&zswap_stored_pages);
-	zswap_pool_pages = zbud_get_pool_size(tree->pool);
+	zswap_pool_pages = zbud_get_pool_size(zswap_pool);
 
 	return 0;
 
@@ -709,47 +738,33 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 	struct zswap_entry *entry;
 	u8 *src, *dst;
 	unsigned int dlen;
-	int refcount, ret;
+	int ret;
 
 	/* find */
 	spin_lock(&tree->lock);
-	entry = zswap_rb_search(&tree->rbroot, offset);
+	entry = zswap_entry_find_get(&tree->rbroot, offset);
 	if (!entry) {
 		/* entry was written back */
 		spin_unlock(&tree->lock);
 		return -1;
 	}
-	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 
 	/* decompress */
 	dlen = PAGE_SIZE;
-	src = (u8 *)zbud_map(tree->pool, entry->handle) +
+	src = (u8 *)zbud_map(zswap_pool, entry->handle) +
 			sizeof(struct zswap_header);
 	dst = kmap_atomic(page);
 	ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
 		dst, &dlen);
 	kunmap_atomic(dst);
-	zbud_unmap(tree->pool, entry->handle);
+	zbud_unmap(zswap_pool, entry->handle);
 	BUG_ON(ret);
 
 	spin_lock(&tree->lock);
-	refcount = zswap_entry_put(entry);
-	if (likely(refcount)) {
-		spin_unlock(&tree->lock);
-		return 0;
-	}
+	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
 
-	/*
-	 * We don't have to unlink from the rbtree because
-	 * zswap_writeback_entry() or zswap_frontswap_invalidate page()
-	 * has already done this for us if we are the last reference.
-	 */
-	/* free */
-
-	zswap_free_entry(tree, entry);
-
 	return 0;
 }
 
@@ -758,7 +773,6 @@ static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset)
 {
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry;
-	int refcount;
 
 	/* find */
 	spin_lock(&tree->lock);
@@ -770,20 +784,12 @@ static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset)
 	}
 
 	/* remove from rbtree */
-	rb_erase(&entry->rbnode, &tree->rbroot);
+	zswap_rb_erase(&tree->rbroot, entry);
 
 	/* drop the initial reference from entry creation */
-	refcount = zswap_entry_put(entry);
+	zswap_entry_put(tree, entry);
 
 	spin_unlock(&tree->lock);
-
-	if (refcount) {
-		/* writeback in progress, writeback will free */
-		return;
-	}
-
-	/* free */
-	zswap_free_entry(tree, entry);
 }
 
 /* frees all zswap entries for the given swap type */
@@ -797,13 +803,12 @@ static void zswap_frontswap_invalidate_area(unsigned type)
 
 	/* walk the tree and free everything */
 	spin_lock(&tree->lock);
-	rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode) {
-		zbud_free(tree->pool, entry->handle);
-		zswap_entry_cache_free(entry);
-		atomic_dec(&zswap_stored_pages);
-	}
+	rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode)
+		zswap_free_entry(entry);
 	tree->rbroot = RB_ROOT;
 	spin_unlock(&tree->lock);
+	kfree(tree);
+	zswap_trees[type] = NULL;
 }
 
 static struct zbud_ops zswap_zbud_ops = {
@@ -815,20 +820,14 @@ static void zswap_frontswap_init(unsigned type)
 	struct zswap_tree *tree;
 
 	tree = kzalloc(sizeof(struct zswap_tree), GFP_KERNEL);
-	if (!tree)
-		goto err;
-	tree->pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops);
-	if (!tree->pool)
-		goto freetree;
+	if (!tree) {
+		pr_err("alloc failed, zswap disabled for swap type %d\n", type);
+		return;
+	}
+
 	tree->rbroot = RB_ROOT;
 	spin_lock_init(&tree->lock);
 	zswap_trees[type] = tree;
-	return;
-
-freetree:
-	kfree(tree);
-err:
-	pr_err("alloc failed, zswap disabled for swap type %d\n", type);
 }
 
 static struct frontswap_ops zswap_frontswap_ops = {
@@ -900,9 +899,16 @@ static int __init init_zswap(void)
 		return 0;
 
 	pr_info("loading zswap\n");
+
+	zswap_pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops);
+	if (!zswap_pool) {
+		pr_err("zbud pool creation failed\n");
+		goto error;
+	}
+
 	if (zswap_entry_cache_create()) {
 		pr_err("entry cache creation failed\n");
-		goto error;
+		goto cachefail;
 	}
 	if (zswap_comp_init()) {
 		pr_err("compressor initialization failed\n");
@@ -912,6 +918,7 @@ static int __init init_zswap(void)
 		pr_err("per-cpu initialization failed\n");
 		goto pcpufail;
 	}
+
 	frontswap_register_ops(&zswap_frontswap_ops);
 	if (zswap_debugfs_init())
 		pr_warn("debugfs initialization failed\n");
@@ -920,6 +927,8 @@ pcpufail:
 	zswap_comp_exit();
 compfail:
 	zswap_entry_cache_destory();
+cachefail:
+	zbud_destroy_pool(zswap_pool);
 error:
 	return -ENOMEM;
 }